adulau/napkin-text-analysis
1
0
Fork 0
mirror of https://github.com/adulau/napkin-text-analysis.git synced 2024-11-22 01:47:06 +00:00
Code Issues Projects Releases Packages Wiki Activity

fix: [bug] email was missing + first value of the ranked set was missed

Browse source
This commit is contained in:
Alexandre Dulaunoy 2020-10-13 07:24:35 +02:00
parent a313b14410
commit 9fb0cc8488
Signed by: adulau
GPG key ID: 09E2CD4944E6CBCD
1 changed files with 5 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
bin/napkin.py
View file

@ -9,6 +9,8 @@ import simplejson as json
from tabulate import tabulate from tabulate import tabulate
import cld3 import cld3
version = "0.9"
parser = argparse.ArgumentParser(description="Extract statistical analysis of text") parser = argparse.ArgumentParser(description="Extract statistical analysis of text")
parser.add_argument('-v', help="verbose output") parser.add_argument('-v', help="verbose output")
parser.add_argument('-f', help="file to analyse") parser.add_argument('-f', help="file to analyse")
@ -69,7 +71,7 @@ doc = nlp(text)
analysis = ["verb", "noun", "hashtag", "mention", analysis = ["verb", "noun", "hashtag", "mention",
"digit", "url", "oov", "labels", "digit", "url", "oov", "labels",
"punct"] "punct", "email"]
if args.token_span and not disable: if args.token_span and not disable:
analysis.append("span") analysis.append("span")
@ -132,7 +134,7 @@ for entity in doc.ents:
redisdb.zincrby("labels", 1, entity.label_) redisdb.zincrby("labels", 1, entity.label_)
if args.o == "json": if args.o == "json":
output_json = {"format":"napkin"} output_json = {"format":"napkin", "version": version}
for anal in analysis: for anal in analysis:
more_info = "" more_info = ""
if args.analysis == "all" or args.analysis == anal: if args.analysis == "all" or args.analysis == anal:
@ -143,7 +145,7 @@ for anal in analysis:
more_info = "for {}".format(args.token_span) more_info = "for {}".format(args.token_span)
if args.o == "readable": if args.o == "readable":
previous_value = None previous_value = None
x = redisdb.zrevrange(anal, 1, args.t, withscores=True, score_cast_func=int) x = redisdb.zrevrange(anal, 0, args.t, withscores=True, score_cast_func=int)
if args.o == "csv": if args.o == "csv":
print() print()
elif args.o == "readable": elif args.o == "readable":